Profile Job Results
Jobs
jgdvve3zg
Results Ready
Name
trocr_float_TrOCREncoder
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]Completion Time
1/31/2026, 7:32:28 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
14.7 ms
Estimated Peak Memory Usage
7 ‑ 161 MB
Compute Units
NPU
603
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.30 s | 350‑356 MB |
Subsequent App Load | 457 ms | 50‑206 MB |
Inference | 14.7 ms | 7‑161 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
| htp_options.device_id | 1 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device